Research map / Image generation / Image restoration
Single Image Reflection Suppression
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use Laplacian data fidelity with an l0 gradient-sparsity prior instead of the compared single-image methods | Single Image Reflection Suppression · Synthetic blend Fig. 5a | PSNR: 18.33 -> 20.37 | Helped |
| Use Laplacian data fidelity with an l0 gradient-sparsity prior instead of the compared single-image methods | Single Image Reflection Suppression · Synthetic blend Fig. 5a | SSIM: 0.86 -> 0.93 | Helped |
| Use Laplacian data fidelity with an l0 gradient-sparsity prior instead of the compared single-image methods | Single Image Reflection Suppression · Synthetic blend Fig. 5e | PSNR: 15.63 -> 15.72 | Helped |
| Use Laplacian data fidelity with an l0 gradient-sparsity prior instead of the compared single-image methods | Single Image Reflection Suppression · Synthetic blend Fig. 5e | SSIM: 0.72 -> 0.81 | Helped |
| Use Laplacian data fidelity with an l0 gradient-sparsity prior instead of the compared single-image methods | Single Image Reflection Suppression · Synthetic blend Fig. 5i | PSNR: 20.17 -> 22.35 | Helped |
| Use Laplacian data fidelity with an l0 gradient-sparsity prior instead of the compared single-image methods | Single Image Reflection Suppression · Synthetic blend Fig. 5i | SSIM: 0.93 -> 0.96 | Helped |
| Use Laplacian data fidelity with an l0 gradient-sparsity prior instead of the compared single-image methods | Single Image Reflection Suppression · Synthetic blend Fig. 5m | PSNR: 17.76 -> 18.09 | Helped |
| Use Laplacian data fidelity with an l0 gradient-sparsity prior instead of the compared single-image methods | Single Image Reflection Suppression · Synthetic blend Fig. 5m | SSIM: 0.85 -> 0.89 | Helped |
| Increase the regularization parameter (ablation) | Single Image Reflection Suppression · Images with reflections | Reflection suppression and transmission detail retention | Mixed |
| Use Laplacian data fidelity rather than pixel-domain fidelity (ablation) | l0 gradient-sparsity image smoothing · Synthetic toy blend Fig. 2 | Transmission detail retention | Helped |
Closest papers by meaning
- Fast Single Image Reflection Suppression via Convex Optimization (CVPR 2019 · similarity 0.93)
- Revisiting Single Image Reflection Removal In the Wild (CVPR 2024 · similarity 0.85)
- PolarFree: Polarization-based Reflection-Free Imaging (CVPR 2025 · similarity 0.84)
- Flash-Split: 2D Reflection Removal with Flash Cues and Latent Diffusion Separation (CVPR 2025 · similarity 0.84)
- FIRM: Flexible Interactive Reflection ReMoval (AAAI 2025 · similarity 0.84)
- Polarization Guided Mask-Free Shadow Removal (AAAI 2025 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.